Please create an account to participate in the Slashdot moderation system

 


Forgot your password?
Close
typodupeerror
×
AMD Data Storage Intel Upgrades

Battle of the SATA 3.0 Controllers 138

Posted by timothy from the more-like-a-skirmish dept.
Deathspawner writes "Think that all SATA 3.0 (6Gb/s) controllers are alike? As Techgage explores, that's not the case. While most SATA 3.0 controllers do deliver the performance promised, the most popular offering on the market does not — at least where bandwidth-busting SSDs are concerned. The controller comes from Marvell, and was bundled on all motherboards prior to AMD and Intel launching their own SATA 3.0 solutions. In some cases, Marvell's controller is half as fast as the others, making it no better than a SATA 2.0 controller. For those with motherboards using a Marvell controller, the solutions are few; build a new PC, or invest in a super-expensive add-in card."
This discussion has been archived. No new comments can be posted.

Battle of the SATA 3.0 Controllers More

Battle of the SATA 3.0 Controllers

Comments Filter:

  • Can anyone say, "class action lawsuit"? It might not work, but if it's actually promising the performance of the spec and doesn't deliver that seems actionable to me (a legal lay person).

    • Re: (Score:2)

      by jhoegl ( 638955 )
      In the United States of Corporate America or elsewhere?

      Shit, they could have the disclaimer that its terrible in the fucking watermark and still get away with it.
      Buyer beware in deed.
      • I think you're misunderstanding: they only promise to deliver "up to" the advertised speeds!

        • Re:I can think of a third option, but it may fail. (Score:4, Insightful)

          by newcastlejon ( 1483695 ) on Thursday September 01, 2011 @03:29PM (#37279460)
          Here's a rule of thumb I've found useful: whenever an ad says "up to" you need to replace it with "usually less than".
          • Then how do you distinguish those vendors "who want to cheat" from those that are just innocently pointing out that the spec'ed maximal speed can only be reached if the disk is able to supply it too (which would be another reason to say "up to").

            • Well, actually saying that it requires a sufficiently fast disk would be a good start.

              Honesty about the limitations of your products is a big incentive to me, but I'm odd that way.

          • Well, yeah. My understanding is that the meaning of "up to" is "usually less than" by definition. No matter what quantity we're talking about. Now, if you meant "up to" should be replaced by "designed to be less than, certain lots might peak at this spec, but we guarantee that none of these parts will ever exceed this performance" then I could agree with that.

          • similarly, if the price says "from only $x" that almost certainly means "but if you actually want to use it, at least 50% more than $x"

      • You mean the Corporate states of america where nVida just got the crap kicked out of them in a class action lawsuit about a year ago [engadget.com]? To the tune of having to give all affected brand new laptops?

        Yea, kindly refrain from spouting nonsense. Companies regularly get hit and found liable in class action lawsuits.

        • You mean the Corporate states of america where nVida just got the crap kicked out of them in a class action lawsuit about a year ago [engadget.com]? To the tune of having to give all affected brand new laptops?

          You mean laptops worth $1,000 less than the laptops they were replacing? [blogspot.com]
          "Milberg LLP, negotiated that they could only receive an entry-level Compaq CQ50, often worth over a thousand dollars less than the computer they would be replacing. "

          If I total your Porsche and have to buy you a Kia I don't think I "got the crap kick out" of me, in fact I'd say I won.

          • Sorry they actually changed the settlement [nvidiasettlement.com] to a $250 Compaq Presario CQ56-115DX with a single core 2.3ghz AMD V140. [newegg.com]

            If you're replacing a [nvidiasettlement.com] $1300 HP TX1000 Tablet with AMD 64X2 2.0GHz [notebookreview.com] you may choose a $450 ASUS Eee PC Tablet with Atom N570 and 1gb ram. [newegg.com]

            Note you do have to mail in your old laptop to receive one of these and there are no other laptops to choose from, you either get a $250 laptop or if you had a tablet you receive a $450 Asus Eee PC.

            Nvidia won, customers lost. I hate Nvidia

            • They still got a free laptop, which, considering it was a CLASS ACTION SUIT, is pretty darn amazing. And I think the entire thing is overblown-- theyre still getting a brand new tablet convertible laptop, its still got a dual core processor, and they still got at least a few years of service out of the original part.

              Arguing that nVidia WON is ridiculous; most customers didnt have to lift a finger, and are getting a brand new laptop, with no legal risk-- and in todays litigious society thats pretty big.

    • Comment removed based on user account deletion

    • You must not live in the U.S..

      Hell, didn't the SCOTUS just rule that a company can preemptively block a class action lawsuit just by saying in their EULA "You are not allowed to sue us in a class action law suit? (or it's legalese equivalent)" Gee, I wonder how many EULA's don't include that language now? I'm betting not many...

      • Re: (Score:2)

        by Tsingi ( 870990 )

        You must not live in the U.S..

        Hell, didn't the SCOTUS just rule that a company can preemptively block a class action lawsuit just by saying in their EULA "You are not allowed to sue us in a class action law suit? (or it's legalese equivalent)" Gee, I wonder how many EULA's don't include that language now? I'm betting not many...

        "Noitercsid ruo ta tuo uoy ekat ot sajnin dnes ot su ezirohtua uoy, erawtfos siht gnisu yb, eromrehtfuf dna.

    • I'd be shocked to see that work. An enormous number of data links are named for, colloquially identified by, or associated with, their theoretical maximum speeds; but not hitting those often, if at all, is more or less standard. Unless Marvell or the motherboard vendor actually made specific performance claims that they failed to meet, rather than just claims of SATA revision 3.0 compatibility, their lie factor would be no greater than that of numerous other protocol silicon vendors(ethernet, wifi, etc.) wh

      • Re: (Score:2)

        by BigSes ( 1623417 )
        It's odd, but I specifically remember the days of computing where you got exactly what you paid for. For example, a double-speed CD-ROM drive performed at the promised 300kb/s rate, no matter the manufacturer. I think we have largely gotten away from that in modern times, unfortunately.
        • I think that it depends more on the specific type of gear, or standard. CD-ROM, a close descendant of the essentially 'streaming' CD audio setups, where going below required data rate would mean nasty audio skips, and a RAM buffer to make use of going above required data rate was too expensive to be assumed, still had a lot of those assumptions baked into it(enough so that, unlike HDDs, they used fussier and more expensive variable-speed rotation to keep the linear velocity of the read head above the mediu

    • Can anyone say, "class action lawsuit"? It might not work, but if it's actually promising the performance of the spec and doesn't deliver that seems actionable to me (a legal lay person).

      The only lawsuit I could see out of this is perhaps Marvell using the SATA-IO's copyrighted logos and terminology implying compliance when it actually doesn't. I can't seem to find any datasheets for 9172, but I'm not trying very hard.

      Now, if the SATA III standard is so loose that it's still within specs... blame the spec, not the player.

  • What do you expect? (Score:5, Funny)

    by MrEricSir ( 398214 ) on Thursday September 01, 2011 @02:52PM (#37278882) Homepage

    Ever since they got bought by Disney, Marvell's disk controllers were never the same.

  • Tested True (Score:3)

    by Metabolife ( 961249 ) on Thursday September 01, 2011 @02:53PM (#37278898)

    I initially tried the Marvell controller on my Gigabyte X58 board for a new Agility 3. It was barely getting 230MB/s reads, and it was capped. It eventually failed to detect the drive, so I tried the Intel SATA 2 controller instead. Not only did the drive detect, but I now get ~250MB/s reads (faster random too I've read). I should've known that the company notorious for their freezing SSD controllers would do no better with the SATA controllers.

    • Could it be that they have better controllers now? I just tested the read speeds with a Marvell controller on an ASRock board and a Marvell-controlled SSD (Crucial m4), which is advertised as having 'up to 415 MB/s' reads. The results of six runs of hdparm -t fall between 383 and 426 (this one twice!) MB/s.

  • Replace MOBO is not a solution?
    Oh Noes $50 dollars!

    • Replace MOBO is not a solution? Oh Noes $50 dollars!

      \ What piece of shit motherboards are you buying? My last ASUS mobo was like $289 from Newegg....

      • I was going to say, the motherboard should be the 2nd most expensive component in your typical computer. $50 one is seriously cutting a corner in a way to make almost everything else you buy work at half efficiency. If the mobo isn't close to the price of your CPU, you either A. are running a system that was purely designed to be a cheap piece of crap to handle basic things and you don't really have a reason to care if you are running SATA 3 or plain old fashioned IDE. Or B. you are running a high end syste

        • Re: (Score:2)

          by h4rr4r ( 612664 )

          Way to prove you have no idea what you are talking about. Go buy some cheap and expensive mobos, compare them. See how the CPU is the same no matter what board you use so long as they are the same speed connectors and such.

          I spent more on my SSD and video card than anything else. Keep telling me my machine is low end while you waste your money.

          • And how the mobo-maker doesnt actually make the chips on the board, they just put them together with a BIOS.

            Theyre sort of like a general contractor, what matters is who the real vendors are.

          • Re: (Score:2)

            by Bengie ( 1121981 )

            Go buy a bunch of $50 motherboards and a bunch of $150 motherboards. Now wait 5 years of them running 24/7 and see which ones have the fewest problems. One pays for quality. Go purchase a $25 800watt PSU and load test it, let me know how that goes and tell me quality doesn't matter.

            Last time I purchased a $50 mobo, was because I was 13 years old and mowed lawns for money.

      • and guess what, yours is not 5+ times faster than his. It does have sata3, but ...

        • Go look at what you get for $50 in the way of a motherboard on Newegg right now. I assure you, it's going to be a horrible piece of crap, useless for 90% of applications and builds.

          I mean, what the hell, is it a P4 mobo or something we're talking about here? Or something made post-2005?

          • Re: (Score:2)

            by h4rr4r ( 612664 )

            Yeah, I was off a little, what can I say I got my last Mobo on sale. Turns out it runs almost $80 now. AM3 board and yes I was including mail in rebate.

          • http://www.newegg.com/Product/Product.aspx?Item=N82E16813130593R [newegg.com]

            1155, MSI, no USB3 nor SATA3, nor overclocking, but apart from that, perfectly serviceable. Meets the needs of, actually would be an upgrade for, *everyone* I know.

          • Hey look, its a $65 motherboard with 4 star rating capable of running an i3! [newegg.com]

            Whats that, you want to know what happens when the caps blow out after 4 years of use? Why, I go buy another $65 motherboard!

            Sure is a strange sense of value folks have, thinking someone should build a rig with a $100 processor and a $100 video card and a $40 hard drive, and then drop $300 on the motherboard.

            • Re: (Score:2)

              by Trogre ( 513942 )

              Whats that, you want to know what happens when the caps blow out after 4 years of use? Why, I go buy another $65 motherboard!

              Yes, but what happens to the old motherboard after that? So you now have two motherboards in a period when you only needed one (unless you were planning on upgrading at that time anyway). Unless the caps can be easily replaced (not always the case) you won't be able to donate it to a school or youth centre and have just created more unnecessary toxic waste.

              Where possible, please tr

              • You send it to a recycling center. Apple will take care of it for free, i believe. And replacing a mobo every 4 years really isnt that bad, nor do I think it to be the "average case" with $65 mobos. You can get mobos @ $65 that have NO capacitor issues whatsoever, thats just about the only big issue you MIGHT run into with a cheap unit (other than insufficient cooling, which is easy to fix).

                And asking me to pay 4x as much on some theory that "more expensive means more reliable" despite no real evidence t

                • If you're throwing modern PCs out after 4 years, you're a fool.

                  Anything introduces in the past 4 years is likely to be dual-core and capable of fitting 4GB of RAM. Put a modern OS on that and you have something that will work just fine for regular users for another 4-6 years if no parts die.

                  We priced out a new Thinkpad T series this week and compared it to what I already have:

                  - 8GB RAM (my 4-year old T61p has 4GB and can fit 8GB RAM), sure it might be DDR3 instead of DDR2 but that doesn't get you a w

                  • If you're throwing modern PCs out after 4 years, you're a fool.

                    Er, Im not. I was specifically saying "if the motherboard dies after 4 years because it was only $65, you recycle it and get a new one".

                    I certainly dont think it makes sense to spend $1300 to get top end parts to try to squeeze 8-9 years out of it rather than just getting a $450 pc and hoping for 6-7.

            • Re: (Score:2)

              by Bengie ( 1121981 )

              I expect all hardware I own to run 24/7, not until it dies, but until I no longer have use for it. If my mobo dies when I'm relying on it to work, then it was bad.

              "Look, I found this car for $1000 cheaper. The head gasket goes bad every 4 years, but I still save money in the long run."

              Yeah, if you don't value your time.

      • You overspent. Anything over about $150 is just wasteful. That number is opinion to a limited degree, but buying the top-end mobo almost never a good value.

        I usually wouldnt go over about $180 for a cpu, and $100 for a mobo, and these days probably not over about $100 for the cpu either.

    • The problem is that most of the motherboards that came with this crappy chip were a lot more than $50. Like mine. It has 6 memory slots so I have (and do) have 24 gig of ram. Also, USB3, eSATA, and a total of 12 SATA ports. And for some people who actually use this (It is a VM development machine) it is actually needed. So can you give me a $50 motherboard with all that? How about for $100. And I would like to reuse my DDR3 ram, and LGA1366 i950, if it is not too much trouble.

      • Re: (Score:2)

        by h4rr4r ( 612664 )

        An AM3 board should be findable for $100 that does that. Not going to have 6 slots though, 4 though. I run VMs on servers, 256GB of RAM not a measly 24GB.

        • So once you add the new CPU, (Can't fit an i905 into an AMD motherboard) and the more expensive memory to have it at least 24 gig, it is well more than 10 times that $50. And it is a development workstation. VMs at will with no change management, unlike the VM server.

          • Re: (Score:2)

            by h4rr4r ( 612664 )

            Change management on a dev server?
            Your job sucks.

            • Production servers, and development workstations. Works for me. :) Why spend the $5000-10000 for high availability and high speed drive arrays for development, when a $1500 workstation will do it just as well?

              • Re: (Score:2)

                by h4rr4r ( 612664 )

                No one said anything about high availability, and if you want to dev on slow drives have fun.

  • The cheapest one is crappiest? Say it ain't so! (Score:5, Interesting)

    by jandrese ( 485 ) <kensama@vt.edu> on Thursday September 01, 2011 @02:55PM (#37278936) Homepage Journal
    This happens all the time with computers, but especially with drive controllers it seems. The guy who rushes his half baked solution to market first at the lowest price ends up with millions of copies in nearly every computer in the world. Then a couple of years later when people start really using them, they discover that in fact the chip is full of bugs and slow and corrupts your data. It happened with the CMD 640 back when IDE first came out, the SiI 3112 when SATA first came out, and now it's happening against with SATA2. Most early Firewire controllers were total crap too, and the cheap ones still are.

    The worst part is that nearly every peripheral card manufacturer is going to use that same chip because it's the cheapest. So even if you try to get around a buggy chip on your motherboard by buying a PCIe card, you'll just end up with a second copy of that broken chip. It's infuriating and I don't expect the situation to change anytime soon. That is why I always wait when a new storage access standard comes out, it's just a solid bet that the first generation chips will be way more trouble than they're worth.
    • Virtually everything JMicron has ever released should probably be mentioned here as well. Those guys really know how to crank up the quality...

    • the SiI 3112 when SATA first came out,

      WHY WHY DID YOU BRING THAT UP!!! I thought I wiped that bit of my life from my memory. It was traumatic. I still have sleepless nights watching my computer randomly not recognise my 2TB array, and watching the default Linux kernel driver for that POS kernel panic for no reason.

      I remember having actual sleepless nights getting that piece of shit to work too. I remember having to install Linux on another drive, then compiling in the appropriate drivers, then using that linux to install linux to my other drive

  • Other option (Score:3)

    by the_humeister ( 922869 ) on Thursday September 01, 2011 @02:56PM (#37278962)

    Don't be at the front of the technology curve when buying stuff. Let the other guy take the brunt of it all (thank you other guy for testing these things for the rest of us).

    • Re: (Score:2)

      by Gondola ( 189182 )

      I tried that when I purchased the ASUS P8P67 motherboard. It had *tons* of reviews, and was one of the top-rated LGA1155 boards with more than 100 reviews.

  • It was the first controller on the market. It's got two ports each rated for 6Gbit/sec and it's connected via a single PCI-E x1 lane that's theoretical maximum is 5Gbit/sec.

    Nobody should have been surprised by this at all. The information was readily available.

    Basically, it's suitable for a single device that's sata6, and won't outperform the sata3 controller in some areas.

    The device was only meant as a stop gap for bleeding edge users to get the capability.

  • Marvell can be hit or miss sometimes. I remember the issues I had when I built a system for someone that had a 10/1000 ethernet controller built in. I can actually think of a few reasons why the numbers are lower. First of course is the obvious marevell has been sending out the previous generation of chips to manufactures simply to clear old stock. Most people won't notice a difference anyway. If you're already on a SSD, would you really notice a 150mb/s bump? Prolly not. Then again it could simply b

  • From TFA:

    This isn't to say that Marvell isn't at a disadvantage, however. AMD and Intel both have internal buses to take advantage of, so their SATA 3.0 solutions are basically unrestricted. Marvell on the other hand has to make use of a PCIe lane in order to get its bandwidth, which for a 2.0 lane is 500MB/s. After overhead, that number effectively becomes around 400MB/s, which is about where we saw the drive's read speed basically cap at.

    That kind of writing makes me question the professionalism of Techgage. My God, what a mess. Is he correct? Should I believe his measurements? I really don't know.

    • In fact, it probably ranks as top 25% believable quotes on Slashdot. His writing style could use a little work (who am I to judge, I write like crap too), but his technical eval seems legit. It sounds pretty logical to me:

      You got a fast device (SSD) on a fast bus (SATA3) connected to a slower bus (PCIe 2.0 1x) connected to the Northbridge. What's the result? Bottleneck at the slowest part (PCIe). Toss in an overhead estimate of 20%, and you get a practical top speed of 400MB/sec.

      When switching down to small

  • > For those with motherboards using a Marvell controller, the solutions are few; build a new PC, or invest in a super-expensive add-in card.

    $30 to $60 for a Sata 3 controller card on Amazon depending on number of ports and other factors. I haven't built a PC in awhile (I tend to overbuild and then keep them for a long time) but it seems to me that building a new PC isn't *that* cheap, yet.

    It's very useful information about the Marvell controller, and I will be watching for that. But the conclusion appe

    • Re: (Score:3)

      by Vairon ( 17314 )

      To get good SATA 3 performance you will need to spend ~ $160 or more for a controller card with a decent chipset and multi-lane PCI Express support. If you actually look at all the cheap SATA 3 controller cards for sale on Amazon (or Newegg) you'll find they're all quite similar.

      Here's some examples from Amazon in the price range you mentioned:

      StarTech PEXSAT32 $38
      * Marvell 9128 Chipset
      * PCIe x1 lane

      Sybausa SY-PEX40032 $32
      * Marvell 9128 Chipset
      * PCIe x1 lane

      ASRock 2-Port SATA 3.0 $26
      * Marvell 9123 Chipset
      *

      • Good point. Still, $160 is less than the cost of a new PC, I think, based on the last one I built two years ago.

        • Re: (Score:2)

          by Vairon ( 17314 )

          That $25 board contains a ASMedia asm1061 sata 3 chipset. I could find no benchmarks of it alone. However looking at the design it is unlikely to do much better than the Marvel chipset talked about in this article. The reason for this is that the card uses only a single pci-express lane. As the article discussed, this is also Marvel's biggest weakness. PCI-Express 2.0 has a maximum bandwidth of 500MB/sec per lane. That is ~ 400MB/sec usable by the device after pci-express overhead is taken into account. Any

      • Trusting a typical performance benchmark is like trusting now many pounds you can bench as a measure of overall health. Yes, benchmarks do provide some information about the relative performance of products, but it's by no means a complete picture!

        When you are evaluating performance of a system, it's important to consider all aspects of system performance, and not get too hung up on any single factor.

        Recently, we did a server upgrade to using SSDs in our database servers. The performance difference was dram

  • Heck, they're only about GBP10-12 in the UK. They ought to be even cheaper in the US.

    • Re: (Score:2)

      by Vairon ( 17314 )

      Every cheap sata 3 controller cards I've come across all contain the same (or similar) Marvel chipset as the article's author is complaining about. They also all use only a single PCI-Express lane instead of multiple lanes like the expensive and fast controller cards do.

  • It's not always the controller's fault (Score:5, Informative)

    by mariushm ( 1022195 ) on Thursday September 01, 2011 @03:57PM (#37279820)

    It's not always the fault of the controllers, it can also be the way they're connected to the system.

    These onboard controllers are connected to the system using PCI Express x1 - it's literally just like plugging them into a x1 slot only they're directly on the motherboard. The problem is there are two versions of PCI Express - the older PCI Express 1.0 provides 250 MB/s in each direction, while PCI Express 2.0 provides 500 MB/s in each direction.

    AMD motherboards only had PCI Express 2.0 lanes but Intel had a mix of 2.0 lanes and 1.0 lanes - the most common was 32 x 2.0 lanes (for 2 x x16 lanes for graphics cards) and about 6 x 1.0 lanes coming from the southbridge. So motherboards manufacturers had to either use 1 lane from southbridge and get only 250 MB/s in each direction or resort to using some multiplexing chips that take 2 or more lanes and create a x4 path for the controller. More recently, motherboards detect if there is a card on the second pci express x16 and if there's nothing there, they "borrow" a few of those unused lanes to improve the performance of the various controllers integrated on the motherboard.

    See this Anandtech article, it explains better than I can explain: http://www.anandtech.com/show/2973/6gbps-sata-performance-amd-890gx-vs-intel-x58-p55/2 [anandtech.com]

    But the point is even if the pci express 2.0 is used, there's only 500 MB/s in each direction, SATA 6 gbps means that a maximum of 750 MB/s should be reachable - very few motherboards connect the controllers to more than one 1x lane so even if the controller could reach 750 MB/s, you won't get it.

    This is nothing new - remember the gigabit network cards on PCI? The whole PCI system on your computer can do 133 MB/s and a gigabit link can do about 110 MB/s - would you sue anyone if you plug 4 pci cards in your system and can't reach a throughput higher than 133 MB/s ?

  • Marvell's controller is half-fast

  • First to market = first to fail (Score:3)

    by billcopc ( 196330 ) <vrillco@yahoo.com> on Thursday September 01, 2011 @04:33PM (#37280210) Homepage

    Does Marvell do anything right ? I know their network interfaces are pretty dodgy, as were their SATA 2.0 kludges.

    They know they're a shit company, which is why they rush things to market. Think of all the asian motherboard and add-on manufacturers that are dying to be the first to stick another starburst buzzword on their shiny boxes. Marvell released a shit product a few months before the good ones came out, so they sold millions of chips.

    If the manufacturers had any standard of quality, we wouldn't have bottom feeders like Marvell, VIA, Broadcom and friends. Like all other things made in China, it's a race to the bottom. Why should we expect otherwise, when their time is so cheap compared to ours ? If I lose a month's work due to corruption, I'm out a good $5k. If they lose a month's work... well they lost less than the cost of the board.

    • Re: (Score:2)

      by fnj ( 64210 )

      All Marvell shit is pretty much junk. It's just plain sad that almost all motherboard vendors stick you with crappy Marvell gigabit, for example. That reason alone was enough to make me choose an Intel brand motherboard for my last build.

  • is the new super expensive now?

    Wow, I must be super rich!

  • Just purchased an ASUS P8P67 motherboard for a brand new Core i7 2600k install; my first new PC in like 5 years. I chose the P8P67 because it had a good assortment of SATA 3 and USB 3 ports for expansion. I had a DVD burner and 3 SATA drives to put into it; I like lots of storage.

    I hooked up the drives, putting my brand new WD Caviar Black 1TB SATA 3 hard drive in the first SATA 3 port, and started installing Windows 7. It seemed to take a long time. The installation finished and I started installing al

    • Basically for SATA-III you really just want to use the Intel (or AMD) native SATA ports and you want to configure the BIOS to put them in AHCI mode and use a relatively modern mobo.

      For Intel you want something based on SandyBridge, LGA 1155 socket, H67 chipset for a consumer workstation or server. Unlike AMD, Intel basically does not support ECC on their consumer cpus.

      If you want to stuff your box full of memory, even with only four slots in a micro-atx form factor, I think you can fit ~16G or so which is

  • Use on-chip AHCI controllers for Sata-III (Score:5, Informative)

    by m.dillon ( 147925 ) on Thursday September 01, 2011 @07:57PM (#37281784) Homepage

    Generally speaking if you want SATA-III to operate satisfactorily you need to use the AHCI controller built into the cpu chipset bundle. That is, the one that Intel and AMD bundle. That will get you a reliable 32-tag-per-port controller. You definitely do not want to use an external controller or a third-party chipset controller (aka Marvell), at least not if you can help it. You won't have a choice if you want hardware RAID, AMD and Intel's controllers don't do RAID (BIOS-based fakeraid doesn't count).

    All chipsets have bugs, even AMD and Intel chipsets. Intel AHCI controllers have problems probing Intel SSDs (go figure) and require a driver workaround to unbrick the port when the problem occurs during probe. AMD chipsets don't mask phy errors during initial training, which creates a lot of superfluous interrupts. Both controllers play fast and loose with the AHCI spec and the AHCI spec itself is pretty badly designed, with tons of issues (though not as badly designed as the immensely idiotic USB HCIs).

    Another big problem is that the firmware controller that runs the chipset side of the AHCI is typically responsible for ALL the SATA ports, which means that hotplug on one port can actually interfere with operations on another. It pisses me off, but there's no avoiding it.

    The external chipsets are even worse. Marvell is a joke. Silicon Image chipsets are full of HARDWARE bugs (not just firmware bugs) which require a lot of workarounds in driver code (for example, you can't abort a soft-reset sequence reliably on a SIL chipset and you can't access the on-chip shared memory while commands are in progress without corrupting any DMA that happens to be occuring).

    The stuff is getting better, slowly. The manufacturers of these chipsets have traditionally not really cared about these sorts of bugs because 99.9% of their users are consumers who don't care. The remaining 0.1% professionals who do care aren't a big enough crowd to make the manufacturers actually fix their firmware.

    SATA at least has the AHCI spec, too bad more chip manufacturers don't use it. If you want to talk wireless and ethernet chipsets matters are far, far worse.

    -Matt (who wrote and maintains DragonFly's AHCI driver)

    • Intel AHCI controllers have problems probing Intel SSDs (go figure)

      I once talked with an engineer from an Intel research lab and found out they worked on SSDs.
      Apparently their highly acclaimed X25s were mostly developed by the research lab, and were to be transitioned over to product development teams.
      And apparently, Intel product development teams wern't as good. Hence why the Intel 510 uses a Marvell SSD controller. :P

      After seeing the Pentium FPU bugs, the Netburst Architecture, FB-DIMMs, and Larrabee, I'm not surprised.

      Props to their research groups though!

Slashdot Top Deals

No spitting on the Bus! Thank you, The Mgt.

Close